Update pylint

.pylintrc

@@ -61,11 +61,11 @@ enable= E0001,E0100,E0101,E0102,E0103,E0104,E0105,E0106,E0107,E0110,
         E0702,E0703,E0704,E0710,E0711,E0712,E1003,E1102,E1111,E0112,
         E1120,E1121,E1123,E1124,E1125,E1126,E1127,E1132,E1200,E1201,
         E1205,E1206,E1300,E1301,E1302,E1303,E1304,E1305,E1306,
-        C0123,C0200,C0303,C1001,
+        C0123,C0200,C0303,C0411,C1001,
         W0101,W0102,W0104,W0105,W0106,W0107,W0108,W0109,W0110,W0120,
         W0122,W0124,W0150,W0199,W0221,W0222,W0233,W0404,W0410,W0601,
         W0602,W0604,W0611,W0612,W0622,W0623,W0702,W0705,W0711,W1300,
-        W1301,W1302,W1303,,W1305,W1306,W1307
+        W1301,W1302,W1303,W1305,W1306,W1307
         R0102,R0202,R0203
 
 
@@ -112,7 +112,9 @@ evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / stateme
 [BASIC]
 
 # Good variable names which should always be accepted, separated by a comma
-good-names=i,j,k,ex,Run,_
+good-names=i,j,k,ex,Run,_,x,y,w,h,d,c,id,it
+
+allowed-redefined-builtins=id,format,dir
 
 # Bad variable names which should always be refused, separated by a comma
 bad-names=foo,bar,baz,toto,tutu,tata
@@ -300,7 +302,7 @@ ignored-classes=optparse.Values,thread._local,_thread._local
 # List of members which are set dynamically and missed by pylint inference
 # system, and so shouldn't trigger E1101 when accessed. Python regular
 # expressions are accepted.
-generated-members=
+generated-members=on_error
 
 # List of decorators that produce context managers, such as
 # contextlib.contextmanager. Add to this list to register other decorators that

datumaro/components/dataset.py

@@ -2,8 +2,6 @@
 #
 # SPDX-License-Identifier: MIT
 
-#pylint: disable=redefined-builtin
-
 from contextlib import contextmanager
 from enum import Enum, auto
 from typing import Iterable, Iterator, Optional, Tuple, Union, Dict, List
@@ -18,7 +16,8 @@
     IExtractor, LabelCategories, AnnotationType, DatasetItem,
     DEFAULT_SUBSET_NAME, Transform)
 from datumaro.components.environment import Environment
-from datumaro.components.errors import DatumaroError, RepeatedItemError
+from datumaro.components.errors import (CategoriesRedefinedError,
+    DatumaroError, RepeatedItemError)
 from datumaro.util import error_rollback
 from datumaro.util.log_utils import logging_disabled
 
@@ -78,7 +77,7 @@ def subsets(self):
 
 class DatasetItemStorageDatasetView(IDataset):
     class Subset(IDataset):
-        def __init__(self, parent, name):
+        def __init__(self, parent: 'DatasetItemStorageDatasetView', name: str):
             super().__init__()
             self.parent = parent
             self.name = name
@@ -319,6 +318,11 @@ def categories(self) -> CategoriesInfo:
         else:
             return self._source.categories()
 
+    def define_categories(self, categories: CategoriesInfo):
+        if self._categories or self._source is not None:
+            raise CategoriesRedefinedError()
+        self._categories = categories
+
     def put(self, item):
         is_new = self._storage.put(item)
 
@@ -459,8 +463,7 @@ def __init__(self, source: IDataset = None,
         self._source_path = None
 
     def define_categories(self, categories: Dict):
-        assert not self._data._categories and self._data._source is None
-        self._data._categories = categories
+        self._data.define_categories(categories)
 
     def init_cache(self):
         self._data.init_cache()

datumaro/components/errors.py

@@ -17,6 +17,10 @@ class RepeatedItemError(DatasetError):
     def __str__(self):
         return "Item %s is repeated in the source sequence." % (self.item_id, )
 
+class CategoriesRedefinedError(DatasetError):
+    def __str__(self):
+        return "Categories can only be set once for a dataset"
+
 @attrs
 class MismatchingImageInfoError(DatasetError):
     a = attrib()

datumaro/components/extractor.py

@@ -6,12 +6,12 @@
 from enum import Enum, auto
 from glob import iglob
 from typing import Callable, Iterable, List, Dict, Optional
-import numpy as np
 import os
 import os.path as osp
 
-import attr
 from attr import attrs, attrib
+import attr
+import numpy as np
 
 from datumaro.util.image import Image
 from datumaro.util.attrs_util import not_empty, default_if_none
@@ -541,7 +541,7 @@ def wrap(item, **kwargs):
 
 CategoriesInfo = Dict[AnnotationType, Categories]
 
-class IExtractor: #pylint: disable=redefined-builtin
+class IExtractor:
     def __iter__(self) -> Iterable[DatasetItem]:
         raise NotImplementedError()
 
@@ -614,7 +614,7 @@ def categories(_):
     def categories(self):
         return {}
 
-    def get(self, id, subset=None): #pylint: disable=redefined-builtin
+    def get(self, id, subset=None):
         subset = subset or DEFAULT_SUBSET_NAME
         for item in self:
             if item.id == id and item.subset == subset:
@@ -638,7 +638,7 @@ def __iter__(self):
     def __len__(self):
         return len(self._items)
 
-    def get(self, id, subset=None): #pylint: disable=redefined-builtin
+    def get(self, id, subset=None):
         assert subset == self._subset, '%s != %s' % (subset, self._subset)
         return super().get(id, subset or self._subset)
 

datumaro/components/project.py

@@ -38,7 +38,7 @@ def __len__(self):
             def categories(self):
                 return self.parent.categories()
 
-            def get(self, id, subset=None): #pylint: disable=redefined-builtin
+            def get(self, id, subset=None):
                 subset = subset or self.name
                 assert subset == self.name, '%s != %s' % (subset, self.name)
                 return super().get(id, subset)
@@ -137,15 +137,13 @@ def categories(self):
     def __len__(self):
         return sum(len(s) for s in self._subsets.values())
 
-    def get(self, id, subset=None, \
-            path=None): #pylint: disable=redefined-builtin
+    def get(self, id, subset=None, path=None):
         if path:
             source = path[0]
             return self._sources[source].get(id=id, subset=subset)
         return self._subsets.get(subset, {}).get(id)
 
-    def put(self, item, id=None, subset=None, \
-            path=None): #pylint: disable=redefined-builtin
+    def put(self, item, id=None, subset=None, path=None):
         if path is None:
             path = item.path
 
@@ -277,8 +275,7 @@ def categories(_):
 
         return self.transform(_DatasetFilter)
 
-    def export(self, save_dir: str, format, \
-            **kwargs): #pylint: disable=redefined-builtin
+    def export(self, save_dir: str, format, **kwargs):
         dataset = Dataset.from_extractors(self, env=self.env)
         dataset.export(save_dir, format, **kwargs)
 

datumaro/plugins/voc_format/converter.py

@@ -26,7 +26,7 @@
 )
 
 
-def _convert_attr(name, attributes, type_conv, default=None, warn=True):
+def _convert_attr(name, attributes, type_conv, default=None):
     d = object()
     value = attributes.get(name, d)
     if value is d:

tests/test_voc_format.py

@@ -1,10 +1,10 @@
 from collections import OrderedDict
 from functools import partial
-import numpy as np
+from unittest import TestCase
 import os
 import os.path as osp
 
-from unittest import TestCase
+import numpy as np
 
 from datumaro.components.extractor import (Extractor, DatasetItem,
     AnnotationType, Label, Bbox, Mask, LabelCategories,